Search for: All records

As solar electricity has become cheaper than the retail electricity price, residential consumers are trying to reduce costs by meeting more demand using solar energy. One way to achieve this is to invest in the solar infrastructure collaboratively. When houses form a coalition, houses with high solar potential or surplus roof capacity can install more panels and share the generated solar energy with others, lowering the total cost. Fair sharing of the resulting cost savings across the houses is crucial to prevent the coalition from breaking. However, estimating the fair share of each house is complex as houses contribute different amounts of generation and demand in the coalition, and rooftop solar generation across houses with similar roof capacities can vary widely. In this paper, we present HeliosFair, a system that minimizes the total electricity costs of a community that shares solar energy and then uses Shapley values to fairly distribute the cost savings thus obtained. Using real-world data, we show that the joint CapEx and OpEx electricity costs of a community sharing solar can be reduced by 12.7% on average (11.3% on average with roof capacity constraints) over houses installing solar energy individually. Our Shapley-value-based approach can fairly distribute these savings across houses based on their contributions towards cost reduction, while commonly used ad hoc approaches are unfair under many scenarios. HeliosFair is also the first work to consider practical constraints such as the difference in solar potential across houses, rooftop capacity and weight of solar panels, making it deployable in practice. 

The ever-increasing demand for energy is resulting in considerable carbon emissions from the electricity grid. In recent years, there has been growing attention on demand-side optimizations to reduce carbon emissions from electricity usage. A vital component of these optimizations is short-term forecasting of the carbon intensity of the grid-supplied electricity. Many recent forecasting techniques focus on day-ahead forecasts, but obtaining such forecasts for longer periods, such as multiple days, while useful, has not gotten much attention. In this paper, we present CarbonCast, a machine-learning-based hierarchical approach that provides multi-day forecasts of the grid's carbon intensity. CarbonCast uses neural networks to first generate production forecasts for all the electricity-generating sources. It then uses a hybrid CNN-LSTM approach to combine these first-tier forecasts with historical carbon intensity data and weather forecasts to generate a carbon intensity forecast for up to four days. Our results show that such a hierarchical design improves the robustness of the predictions against the uncertainty associated with a longer multi-day forecasting period. We analyze which factors most influence the carbon intensity forecasts of any region with a specific mixture of electricity-generating sources and also show that accurate source production forecasts are vital in obtaining precise carbon intensity forecasts. CarbonCast's 4-day forecasts have a MAPE of 3.42--19.95% across 13 geographically distributed regions while outperforming state-of-the-art methods. Importantly, CarbonCast is the first open-sourced tool for multi-day carbon intensity forecasts where the code and data are freely available to the research community.